Learning business process simulation models: A Hybrid process mining and deep learning approach✩

被引:11
作者
Camargo, Manuel [1 ,2 ,3 ]
Baron, Daniel [2 ]
Dumas, Marlon [1 ]
Gonzalez-Rojas, Oscar [2 ]
机构
[1] Univ Tartu, Tartu, Estonia
[2] Univ los Andes, Bogota, Colombia
[3] Apromore, Tartu, Estonia
基金
欧洲研究理事会;
关键词
Process mining; Data-driven simulation; Deep learning;
D O I
10.1016/j.is.2023.102248
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Business process simulation is a well-known approach to estimate the impact of changes to a process with respect to time and cost measures - a practice known as what-if process analysis. The usefulness of such estimations hinges on the accuracy of the underlying simulation model. Data-Driven Simulation (DDS) methods leverage process mining techniques to learn business process simulation models from event logs. Empirical studies have shown that, while DDS models adequately capture the observed sequences of activities and their frequencies, they fail to accurately capture the temporal dynamics of real-life processes. In contrast, generative Deep Learning (DL) models are better able to capture such temporal dynamics. The drawback of DL models is that users cannot alter them for what-if analysis due to their black-box nature. This paper presents a hybrid approach to learn process simulation models from event logs wherein a (stochastic) process model is extracted via DDS techniques, and then combined with a DL model to generate timestamped event sequences. The proposed approach allows us to simulate different types of changes, including the addition of new activity types to a process. This latter capability is achieved by encoding the activities by means of embeddings, rather than representing them as one-hot-encoded categories. An experimental evaluation shows that the resulting hybrid simulation models match the temporal accuracy of pure DL models, while partially retaining the what-if analysis capability of DDS approaches. The evaluation also sheds light into the relative performance of multiple embedding approaches to represent the activities.& COPY; 2023 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
引用
收藏
页数:14
相关论文
共 35 条
[1]  
Al-Jebrni A, 2018, PR IEEE I C PROGR IN, P332, DOI 10.1109/PIC.2018.8706282
[2]   Split miner: automated discovery of accurate and simple business process models from event logs [J].
Augusto, Adriano ;
Conforti, Raffaele ;
Dumas, Marlon ;
La Rosa, Marcello ;
Polyvyanyy, Artem .
KNOWLEDGE AND INFORMATION SYSTEMS, 2019, 59 (02) :251-284
[3]   Learning Accurate Business Process Simulation Models from Event Logs via Automated Process Discovery and Deep Learning [J].
Camargo, Manuel ;
Dumas, Marlon ;
Gonzalez-Rojas, Oscar .
ADVANCED INFORMATION SYSTEMS ENGINEERING (CAISE 2022), 2022, :55-71
[4]   Discovering generative models from event logs: data-driven simulation vs deep learning [J].
Camargo, Manuel ;
Dumas, Marlon ;
Gonzalez-Rojas, Oscar .
PEERJ COMPUTER SCIENCE, 2021, 7
[5]   Learning Accurate LSTM Models of Business Processes [J].
Camargo, Manuel ;
Dumas, Marlon ;
Gonzalez-Rojas, Oscar .
BUSINESS PROCESS MANAGEMENT (BPM 2019), 2019, 11675 :286-302
[6]   Automated discovery of business process simulation models from event logs [J].
Camargo, Manuel ;
Dumas, Marlon ;
Gonzalez-Rojas, Oscar .
DECISION SUPPORT SYSTEMS, 2020, 134
[7]  
Chapela-Campa D, 2024, Arxiv, DOI arXiv:2206.14051
[8]   act2vec, trace2vec, log2vec, and model2vec: Representation Learning for Business Processes [J].
De Koninck, Pieter ;
vanden Broucke, Seppe ;
De Weerdt, Jochen .
BUSINESS PROCESS MANAGEMENT (BPM 2018), 2018, 11080 :305-321
[9]   Activity Prediction of Business Process Instances with Inception CNN Models [J].
Di Mauro, Nicola ;
Appice, Annalisa ;
Basile, Teresa M. A. .
ADVANCES IN ARTIFICIAL INTELLIGENCE, AI*IA 2019, 2019, 11946 :348-361
[10]  
Dumas M., 2018, Fundamentals of business process management, VSecond